# claude-memory-kit - Doramagic AI Context Pack > Purpose: pre-work context for the user's host AI. This pack does not prove that the project has been installed, run, or validated. ## Project - canonical_name: `LH8PPL/claude-memory-kit` - capability: Persistent per-project memory for Claude Code — plain markdown committed with your code, captured automatically every turn, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, and a searchable session record down to raw transcripts. - expected_user_outcome: Persistent per-project memory for Claude Code — plain markdown committed with your code, captured automatically every turn, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, and a searchable session record down to raw transcripts. ## Operating Boundaries - Do not claim that the project has been installed, run, called through an API, or used on local files unless separate evidence proves it. - Project facts must come from repo evidence, Claim Graph, or explicit source references. - When a capability is not verified, mark it as unverified instead of completing it as fact. - publish_status: `publishable` - blocking_gaps: none --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Overview & Three-Tier Architecture**: importance `high` - source_paths: README.md, ARCHITECTURE.md, CLAUDE.md, docs/DOCUMENTATION-MAP.md, packages/cli/src/tier-paths.mjs - **Memory Lifecycle: Capture, Compression, Recall**: importance `high` - source_paths: packages/cli/src/compressor.mjs, packages/cli/src/lazy-compress.mjs, packages/cli/src/compress-retry.mjs, packages/cli/src/compress-session.mjs, packages/cli/src/auto-extract.mjs - **Installation & Multi-Agent Wiring (Claude Code and Kiro)**: importance `high` - source_paths: packages/cli/src/install.mjs, packages/cli/src/install-agent.mjs, packages/cli/src/install-kiro.mjs, packages/cli/src/kiro-cli-agent.mjs, packages/cli/src/kiro-ide-hooks.mjs - **Safety, Delete-Guardrail, Health Checks & Failure Modes**: importance `high` - source_paths: packages/cli/src/guard-memory.mjs, packages/cli/bin/cmk-guard-memory.mjs, packages/cli/src/poison-guard.mjs, packages/cli/src/privacy.mjs, packages/cli/src/provenance.mjs ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `f47adec42766fbc09a3dd8b5136fcf0530258310` - inspected_files: `README.md`, `package.json`, `docs/BOOTSTRAP.md`, `docs/CLI.md`, `docs/DOCUMENTATION-MAP.md`, `docs/MCP.md`, `docs/README.md`, `docs/RELEASE-PLAN.md`, `docs/SOURCES.md`, `docs/adr/0001-separate-project-not-fork-youtube-to-slide.md`, `docs/adr/0002-markdown-source-of-truth-over-opaque-db.md`, `docs/adr/0003-per-project-with-future-cross-project-tier.md`, `docs/adr/0004-spec-driven-development-kiro-style.md`, `docs/adr/0005-three-install-paths.md`, `docs/adr/0006-lifecycle-hooks-architecture.md`, `docs/adr/0007-content-addressed-citation-ids.md`, `docs/adr/0008-bank-airgap-deferred-to-future-version.md`, `docs/adr/0009-provenance-frontmatter-per-observation.md`, `docs/adr/0010-raw-transcripts-preserved-indefinitely.md`, `docs/adr/0011-coexistence-with-anthropic-auto-memory.md` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Configuration risk requires verification - Trigger: Project evidence flags a configuration risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.host_targets | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Maintenance risk requires verification - Trigger: Project evidence flags a maintenance risk. Review the linked source before relying on this workflow. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: downstream_validation.risk_items | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: risks.scoring_risks | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 6: Maintenance risk requires verification - Trigger: issue_or_pr_quality=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 7: Maintenance risk requires verification - Trigger: release_recency=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/LH8PPL/claude-memory-kit - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.